DOCSLIB.ORG

A Framenet-Based Approach for Annotating Software Requirements

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
A Framenet-Based Approach for Annotating Software Requirements A FrameNet-based Approach for Annotating Natural Language Descriptions of Software Requirements Waad Alhoshan, Riza Batista-Navarro, Liping Zhao School of Computer Science, University of Manchester, United Kingdom [email protected] {riza.batista, liping.zhao}@manchester.ac.uk Abstract As most software requirements are written in natural language, they are unstructured and do not adhere to any formalism. Processing them automatically—within the context of software requirements engineering tasks—thus becomes difficult for machines. As a step towards adding structure to requirements documents, we exploited frames in FrameNet and applied them to the semantic annotation of software descriptions. This was carried out through an approach based on automated lexical unit matching, manual validation and harmonisation. As a result, we produced a novel corpus of requirements documents containing software descriptions which have been assigned a total of 242 unique semantic frames overall. Our evaluation of the resulting annotations shows substantial agreement between our two annotators, encouraging us to pursue finer-grained semantic annotation as part of future work. Keywords: Semantic Frames, FrameNet, Corpus Annotation, Software Requirements, Requirements Engineering represented as a combination of their lemmatised form 1. Introduction and part-of-speech (POS) tag (e.g., assemble.v, create.v where v stands for verb). Such a frame can then be applied Software requirements play a pivotal role in all system on a piece of text (such as in Example 1) to represent, in a design phases. Requirements are generally written in structured manner, the creation idea that is being natural language, and therefore are unstructured (Ferrari et conveyed. Containing over 1,200 such frames, FrameNet al., 2017a). This however presents a challenge to has become an invaluable resource to the NLP research Requirements Engineering (RE) tasks, e.g. requirements community. analysis, which often necessitate the organisation and management of requirements in a systematic manner Example 1: (Dick et al, 2017). While certain RE tasks (e.g., [The system] Creator [generates] Creating_lexical unit modelling) could benefit from automated analysis, this [records of user activities] Created_entity [each time] can only be facilitated if some structure is applied to the Frequency [the user logs into the system] Cause. otherwise unstructured natural language requirements contained in software descriptions (Ferrari et al., 2017b). Recent studies in RE have explored the application of FrameNet frames to software requirements acquisition One way by which we can add structure to software and analysis. For example, Jha and Mahmoud (2017) descriptions written in natural language is by attaching employed semantic frames (automatically extracted by the machine-readable semantic metadata that captures SEMAFOR semantic role labeller2) as features in training meaning. In documents from the general and scientific machine learning-based models for categorising user domains, this often corresponds to named entities, e.g., reviews of mobile applications. Meanwhile, Kundi and proper names of persons, places, diseases or chemical Chitchyan (2017) proposed a technique for gathering compounds. Software descriptions however do not allude requirements that employed FrameNet frames as the basis to such proper names as often and instead mention generic of linguistic patterns for generating use cases at the early if not abstract concepts (e.g., account creation, file stages of RE. They specifically made use of the deletion) and the participants involved (e.g., user, system). Agriculture frame to demonstrate their approach. As shown in early work by Belkhouche and Kozma (1993) and Rolland and Priox (1992), capturing meaning We consider FrameNet as a rich repository of semantic contained in requirements can be approached by using metadata that can be added to requirements documents in semantic frames: coherent structured representations of order to add structure to them. In this work, we seek to concepts (Petruck, 1997). These representations are based employ FrameNet as the basis of a scheme for capturing on the theory of frame semantics proposed by Fillmore the meaning of software descriptions. To this end, we (1977) whose work formed the basis of FrameNet, an adopt FrameNet semantic frames in annotating software online computational lexicon that catalogues detailed requirements in a corpus of documents written in natural information on semantic frames1 (Baker et al., 1998). For language. To the best of our knowledge, our work is the every frame it contains, FrameNet specifies the following: first attempt to investigate FrameNet as a means for frame title, definition, frame elements (i.e., participants) annotating meaning within requirements documents. In and lexical units, i.e., words that evoke the frame. The this way, we are enriching them with semantic metadata concept of creation, for example, is encoded in FrameNet and hence incorporating structure into them. As a result, as a frame entitled Creating, with frame elements we have produced and made publicly available a resource pertaining to Creator, Created_entity and Beneficiary for the perusal of other members of the research (among many others). Importantly, lexical units that signify the concept is also provided, each of which is 1 https://framenet.icsi.berkeley.edu 2 http://www.cs.cmu.edu/~ark/SEMAFOR/ community: the FrameNet-annotated FN-REQ3 corpus of (e.g., "further), inclusion (e.g., "inclusive"), exclusion natural language requirements documents. (e.g., "excluding"), contradiction (e.g., "nevertheless"), causation (e.g., "because of") and purpose (e.g., "in The rest of this paper is organised as follows. Section 2 order"). The selection of these types was informed by our describes our methods for collecting software observations on the linguistic styles often used in writing requirements documents and annotating them based on the software requirements. Through this process, we were semantic frames contained in FrameNet. In Section 3, we able to evoke candidate semantic frames that denote the present and analyse results of our annotation. Lastly, we meaning of the requirements in our documents. present our conclusions and plans for future work in Section 4. 2.2.2 Validation Deciding which FrameNet semantic frames capture the 2. Methodology meaning expressed in software descriptions was In this section, we present the methods we carried out in performed manually in order to maximise accuracy. For order to construct a corpus of documents containing this task, we employed two annotators. The first annotator sentences of software requirements, and to subsequently (Annotator A) is a requirements engineer with five years annotate them according to FrameNet. of experience in the IT industry. The second annotator (Annotator B) is one of the authors of this paper and is a 2.1 Document Selection PhD candidate whose study is focussed on the use of NLP Our goal is to gather a document set consisting of techniques to support RE tasks. different types of software requirements. As a preliminary Provided with candidate frames obtained in the previous step, we formed a Google search query containing step, the annotators were asked to confirm whether they keywords such as "software description", “natural capture the meaning of a given software description or language requirements" and "software requirements not. This validation process was carried out in accordance specification". Furthermore, we employed snowball with the guidelines we developed which drew inspiration sampling and found additional requirements from various from the FrameNet annotation scheme proposed by sources such as web blogs, research articles (together with (Baker, 2017). Over a four-week period, both annotators their corresponding datasets), lecture materials and were trained in applying these guidelines on the industrial/commercial documents. This step resulted in the annotation of a set of software descriptions from collection of 34 requirements documents varying in documents other than those in our corpus. Afterwards, the 4 length. The NLTK tool for sentence boundary detection entire corpus of 34 documents—together with the was then applied on the 34 documents. After manually candidate semantic frames retrieved in the previous step— 5 verifying the results, a total of 1,148 sentences were was presented to each of Annotators A and B for obtained (corresponding to 21,012 tokens). annotation. We provide Table 1 to show an example of the 2.2 Annotation Procedure details that are presented to an annotator and the kind of judgement that he/she is expected to provide. At the top The annotation was carried out in a semi-automatic row of the table is a sample software description. The first manner. This was facilitated by the two main steps column (LU) lists the lexical units matched by the method described as follows. described in Section 2.2.1. The second and third columns (Start and End) indicate the location of the corresponding 2.2.1 Evoking Frames by Lexical Unit Matching lexical unit in terms of character offsets—useful With the intention of making the annotation process more information in cases where a lexical unit appears multiple efficient, we developed a simple method for automatically times within a description. The fourth column (Retrieved matching words in the software descriptions in our corpus Frames) lists the titles of the frames linked
Load more

Recommended publications
  • Enriching an Explanatory Dictionary with Framenet and Propbank Corpus Examples
    Proceedings of eLex 2019 Enriching an Explanatory Dictionary with FrameNet and PropBank Corpus Examples Pēteris Paikens 1, Normunds Grūzītis 2, Laura Rituma 2, Gunta Nešpore 2, Viktors Lipskis 2, Lauma Pretkalniņa2, Andrejs Spektors 2 1 Latvian Information Agency LETA, Marijas street 2, Riga, Latvia 2 Institute of Mathematics and Computer Science, University of Latvia, Raina blvd. 29, Riga, Latvia E-mail: [email protected], [email protected] Abstract This paper describes ongoing work to extend an online dictionary of Latvian – Tezaurs.lv – with representative semantically annotated corpus examples according to the FrameNet and PropBank methodologies and word sense inventories. Tezaurs.lv is one of the largest open lexical resources for Latvian, combining information from more than 300 legacy dictionaries and other sources. The corpus examples are extracted from Latvian FrameNet and PropBank corpora, which are manually annotated parallel subsets of a balanced text corpus of contemporary Latvian. The proposed approach augments traditional lexicographic information with modern cross-lingually interpretable information and enables analysis of word senses from the perspective of frame semantics, which is substantially different from (complementary to) the traditional approach applied in Latvian lexicography. In cases where FrameNet and PropBank corpus evidence aligns well with the word sense split in legacy dictionaries, the frame-semantically annotated corpus examples supplement the word sense information with clarifying usage examples and commonly used semantic valence patterns. However, the annotated corpus examples often provide evidence of a different sense split, which is often more coarse-grained and, thus, may help dictionary users to cluster and comprehend a fine-grained sense split suggested by the legacy sources.
    [Show full text]
  • Developing a Large Scale Framenet for Italian: the Iframenet Experience
    Developing a large scale FrameNet for Italian: the IFrameNet experience Roberto Basili° Silvia Brambilla§ Danilo Croce° Fabio Tamburini§ ° § Dept. of Enterprise Engineering Dept. of Classic Philology and Italian Studies University of Rome Tor Vergata University of Bologna {basili,croce}@info.uniroma2.it [email protected], [email protected] ian Portuguese, German, Spanish, Japanese, Swe- Abstract dish and Korean. All these projects are based on the idea that English. This paper presents work in pro- most of the Frames are the same among languages gress for the development of IFrameNet, a and that, thanks to this, it is possible to adopt large-scale, computationally oriented, lexi- Berkeley’s Frames and FEs and their relations, cal resource based on Fillmore’s frame se- with few changes, once all the language-specific mantics for Italian. For the development of information has been cut away (Tonelli et al. 2009, IFrameNet linguistic analysis, corpus- Tonelli 2010). processing and machine learning techniques With regard to Italian, over the past ten years are combined in order to support the semi- several research projects have been carried out at automatic development and annotation of different universities and Research Centres. In par- the resource. ticular, the ILC-CNR in Pisa (e.g. Lenci et al. 2008; Johnson and Lenci 2011), FBK in Trento (e.g. Italiano. Questo articolo presenta un work Tonelli et al. 2009, Tonelli 2010) and the Universi- in progress per lo sviluppo di IFrameNet, ty of Rome, Tor Vergata (e.g. Pennacchiotti et al. una risorsa lessicale ad ampia copertura, 2008, Basili et al.
    [Show full text]
  • Integrating Wordnet and Framenet Using a Knowledge-Based Word Sense Disambiguation Algorithm
    Integrating WordNet and FrameNet using a knowledge-based Word Sense Disambiguation algorithm Egoitz Laparra and German Rigau IXA group. University of the Basque Country, Donostia {egoitz.laparra,german.rigau}@ehu.com Abstract coherent groupings of words belonging to the same frame. This paper presents a novel automatic approach to In that way we expect to extend the coverage of FrameNet partially integrate FrameNet and WordNet. In that (by including from WordNet closely related concepts), to way we expect to extend FrameNet coverage, to en- enrich WordNet with frame semantic information (by port- rich WordNet with frame semantic information and ing frame information to WordNet) and possibly to extend possibly to extend FrameNet to languages other than FrameNet to languages other than English (by exploiting English. The method uses a knowledge-based Word local wordnets aligned to the English WordNet). Sense Disambiguation algorithm for linking FrameNet WordNet1 [12] (hereinafter WN) is by far the most lexical units to WordNet synsets. Specifically, we ex- ploit a graph-based Word Sense Disambiguation algo- widely-used knowledge base. In fact, WN is being rithm that uses a large-scale knowledge-base derived used world-wide for anchoring different types of seman- from WordNet. We have developed and tested four tic knowledge including wordnets for languages other than additional versions of this algorithm showing a sub- English [4], domain knowledge [17] or ontologies like stantial improvement over previous results. SUMO [22] or the EuroWordNet Top Concept Ontology [3]. It contains manually coded information about En- glish nouns, verbs, adjectives and adverbs and is organized around the notion of a synset.
    [Show full text]
  • The Hebrew Framenet Project
    The Hebrew FrameNet Project Avi Hayoun, Michael Elhadad Dept. of Computer Science Ben-Gurion University Beer Sheva, Israel {hayounav,elhadad}@cs.bgu.ac.il Abstract We present the Hebrew FrameNet project, describe the development and annotation processes and enumerate the challenges we faced along the way. We have developed semi-automatic tools to help speed the annotation and data collection process. The resource currently covers 167 frames, 3,000 lexical units and about 500 fully annotated sentences. We have started training and testing automatic SRL tools on the seed data. Keywords: FrameNet, Hebrew, frame semantics, semantic resources 1. Introduction frames and their structures in natural language. Recent years have seen growing interest in the task 1.2. FrameNet in Other Languages of Semantic Role Labeling (SRL) of natural language The original FrameNet project has been adapted and text (sometimes called “shallow semantic parsing”). ported to multiple languages. The most active interna- The task is usually described as the act of identify- tional FrameNet teams include the Swedish FrameNet ing the semantic roles, which are the set of semantic (SweFN) covering close to 1,200 frames with 34K LUs properties and relationships defined over constituents (Ahlberg et al., 2014); the Japanese FrameNet (JFN) of a sentence, given a semantic context. with 565 frames, 8,500 LUs and 60K annotated ex- The creation of resources that document the realiza- ample sentences (Ohara, 2013); and FrameNet Brazil tion of semantic roles in natural language texts, such (FN-Br) covering 179 frames, 196 LUs and 12K anno- as FrameNet (Fillmore and Baker, 2010; Ruppenhofer tated sentences (Torrent and Ellsworth, 2013).
    [Show full text]
  • INF5830 Introduction to Semantic Role Labeling
    INF5830 Introduction to Semantic Role Labeling Andrey Kutuzov University of Oslo Language Technology Group With thanks to Lilja Øvrelid, Martha Palmer and Dan Jurafsky INF5830 Introduction to Semantic Role Labeling 1(36) Semantic Role Labeling INF5830 Introduction to Semantic Role Labeling 2(36) Introduction Contents Introduction Semantic roles in general PropBank: Proto-roles FrameNet: Frame Semantics Summary INF5830 Introduction to Semantic Role Labeling 2(36) Introduction Semantics I Study of meaning, expressed in language; I Morphemes, words, phrases, sentences; I Lexical semantics; I Sentence semantics; I (Pragmatics: how the context affects meaning). INF5830 Introduction to Semantic Role Labeling 3(36) Introduction Semantics I Linguistic knowledge: meaning I Meaningful or not: I Word { flick vs blick I Sentence { John swims vs John metaphorically every I Several meanings (WSD): I Words { fish I Sentence { John saw the man with the binoculars I Same meaning (semantic similarity): I Word { sofa vs couch I Sentence { John gave Hannah a gift vs John gave a gift to Hannah I Truth conditions: I All kings are male I Molybdenum conducts electricity I Entailment: I Alfred murdered the librarian I The librarian is dead I Participant roles: John is the `giver', Hannah is the `receiver' INF5830 Introduction to Semantic Role Labeling 4(36) Introduction Representing events I We want to understand the event described by these sentences: 1. IBM bought Spark 2. IBM acquired Spark 3. Spark was acquired by IBM 4. The owners of Spark sold it to IBM I Dependency parsing is insufficient. UDPipe will give us simple relations between verbs and arguments: 1. (buy, nsubj, IBM), (buy, obj, Spark) 2.
    [Show full text]
  • Using Frame Semantics in Natural Language Processing
    Using Frame Semantics in Natural Language Processing Apoorv Agarwal Daniel Bauer Owen Rambow Dept. of Computer Science Dept. of Computer Science CCLS Columbia University Columbia University Columbia University New York, NY New York, NY New York, NY [email protected] [email protected] [email protected] Abstract the notion of a social event (Agarwal et al., 2010), We summarize our experience using a particular kind of event which involves (at least) FrameNet in two rather different projects two people such that at least one of them is aware in natural language processing (NLP). of the other person. If only one person is aware We conclude that NLP can benefit from of the event, we call it Observation (OBS): for FrameNet in different ways, but we sketch example, someone is talking about someone else some problems that need to be overcome. in their absence. If both people are aware of the event, we call it Interaction (INR): for example, 1 Introduction one person is telling the other a story. Our claim We present two projects at Columbia in which we is that links in social networks are in fact made use FrameNet. In these projects, we do not de- up of social events: OBS social events give rise velop basic NLP tools for FrameNet, and we do to one-way links, and INR social events to two- not develop FramNets for new languages: we sim- way links. For more information, see (Agarwal ply use FrameNet or a FrameNet parser in an NLP and Rambow, 2010; Agarwal et al., 2013a; Agar- application.
    [Show full text]
  • Event-Based Knowledge Reconciliation Using Frame Embeddings And
    Knowledge-Based Systems 135 (2017) 192–203 Contents lists available at ScienceDirect Knowle dge-Base d Systems journal homepage: www.elsevier.com/locate/knosys Event-base d knowle dge reconciliation using frame emb e ddings and frame similarity ∗ Mehwish Alam a, Diego Reforgiato Recupero b,d, , Misael Mongiovi c, Aldo Gangemi a,d, Petar Ristoski e a Université Paris 13, 99 avenue JB Clément, Villetaneuse, Paris 93430, France b Università degli Studi di Cagliari, Department of Mathematics and Computer Science, Via Ospedale 72, Cagliari 09124, Italy c CNR, ISTC, Catania, Italy d CNR, ISTC, Via S. Martino della Battaglia 44, Rome, Italy e University of Mannheim, Mannheim, Germany a r t i c l e i n f o a b s t r a c t Article history: This paper proposes an evolution over MERGILO, a tool for reconciling knowledge graphs extracted from Received 6 April 2017 text, using graph alignment and word similarity. The reconciled knowledge graphs are typically used Revised 9 August 2017 for multi-document summarization, or to detect knowledge evolution across document series. The main Accepted 14 August 2017 point of improvement focuses on event reconciliation i.e., reconciling knowledge graphs generated by text Available online 16 August 2017 about two similar events described differently. In order to gather a complete semantic representation of Keywords: events, we use FRED semantic web machine reader, jointly with Framester, a linguistic linked data hub Knowledge reconciliation represented using a novel formal semantics for frames. Framester is used to enhance the extracted event Frame semantics knowledge with semantic frames.
    [Show full text]
  • Out-Of-Domain Framenet Semantic Role Labeling
    Out-of-domain FrameNet Semantic Role Labeling Silvana Hartmann§†, Ilia Kuznetsov†, Teresa Martin§†, Iryna Gurevych§† Research Training Group AIPHES Ubiquitous§ Knowledge Processing (UKP) Lab Department† of Computer Science, Technische Universitat¨ Darmstadt http://www.ukp.tu-darmstadt.de Abstract on a range of benchmark datasets. This is crucial as the demand for semantic textual analysis of large- Domain dependence of NLP systems is one scale web data keeps growing. of the major obstacles to their application in large-scale text analysis, also restrict- Based on FrameNet (Fillmore et al., 2003), ing the applicability of FrameNet semantic FrameNet SRL extracts frame-semantic structures role labeling (SRL) systems. Yet, current on the sentence level that describe a specific FrameNet SRL systems are still only eval- situation centered around a semantic predicate, uated on a single in-domain test set. For often a verb, and its participants, typically the first time, we study the domain depen- syntactic arguments or adjuncts of the predicate. frame dence of FrameNet SRL on a wide range of The predicate is assigned a label, essentially benchmark sets. We create a novel test set a word sense label, that defines the situation and semantic roles for FrameNet SRL based on user-generated determines the of the participants. web text and find that the major bottleneck The following sentence from FrameNet provides Grinding for out-of-domain FrameNet SRL is the an example of the frame and its roles: frame identification step. To address this [The mill]Grinding cause grindsGrinding [the problem, we develop a simple, yet efficient malt]P atient [to grist]Result.
    [Show full text]
  • Verbnet Guidelines
    VerbNet Annotation Guidelines 1. Why Verbs? 2. VerbNet: A Verb Class Lexical Resource 3. VerbNet Contents a. The Hierarchy b. Semantic Role Labels and Selectional Restrictions c. Syntactic Frames d. Semantic Predicates 4. Annotation Guidelines a. Does the Instance Fit the Class? b. Annotating Verbs Represented in Multiple Classes c. Things that look like verbs but aren’t i. Nouns ii. Adjectives d. Auxiliaries e. Light Verbs f. Figurative Uses of Verbs 1 Why Verbs? Computational verb lexicons are key to supporting NLP systems aimed at semantic interpretation. Verbs express the semantics of an event being described as well as the relational information among participants in that event, and project the syntactic structures that encode that information. Verbs are also highly variable, displaying a rich range of semantic and syntactic behavior. Verb classifications help NLP systems to deal with this complexity by organizing verbs into groups that share core semantic and syntactic properties. VerbNet (Kipper et al., 2008) is one such lexicon, which identifies semantic roles and syntactic patterns characteristic of the verbs in each class and makes explicit the connections between the syntactic patterns and the underlying semantic relations that can be inferred for all members of the class. Each syntactic frame in a class has a corresponding semantic representation that details the semantic relations between event participants across the course of the event. In the following sections, each component of VerbNet is identified and explained. VerbNet: A Verb Class Lexical Resource VerbNet is a lexicon of approximately 5800 English verbs, and groups verbs according to shared syntactic behaviors, thereby revealing generalizations of verb behavior.
    [Show full text]
  • Rs and IOS Press
    ECAI 2014 57 T. Schaub et al. (Eds.) © 2014 The Authors and IOS Press. This article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License. doi:10.3233/978-1-61499-419-0-57 Effective and Robust Natural Language Understanding for Human-R obot Interaction Emanuele Bastianelli(‡), Giuseppe Castellucci(•), Danilo Croce(†), Roberto Basili(†), Daniele Nardi() (†) DII, (‡) DICII, (•) DIE - University of Rome Tor Vergata - Rome, Italy {bastianelli,castellucci}@ing.uniroma2.it, {basili,croce}@info.uniroma2.it () DIAG - Sapienza University of Rome - Rome, Italy [email protected] Abstract. Robots are slowly becoming part of everyday life, as knowledge). Moreover, in HRI, different scenarios need to be con- they are being marketed for commercial applications (viz. telepres- sidered. In some situations, e.g. rescue robotic tasks, the precision is ence, cleaning or entertainment). Thus, the ability to interact with crucial and no command misunderstanding is allowed. non-expert users is becoming a key requirement. Even if user ut- Recently, works in the interpretation of natural language instruc- terances can be efficiently recognized and transcribed by Automatic tions for robots in controlled environments have been focused on Speech Recognition systems, several issues arise in translating them specific subsets of the human language. The interpretation process into suitable robotic actions. In this paper, we will discuss both ap- is mainly carried out through the adoption of specific grammars that proaches providing two existing Natural Language Understanding describe the human language allowed. It gives, for example, a robotic workflows for Human Robot Interaction.
    [Show full text]
  • UMCC DLSI: Textual Similarity Based on Lexical-Semantic Features
    UMCC_DLSI: Textual Similarity based on Lexical-Semantic features Alexander Chávez, Antonio Fernández Orquín, Andrés Montoyo, Rafael Muñoz Héctor Dávila, Yoan Gutiérrez, Armando DLSI, University of Alicante Carretera de Collazo, José I. Abreu San Vicente S/N Alicante, Spain. DI, University of Matanzas {montoyo,rafael}@dlsi.ua.es Autopista a Varadero km 3 ½ Matanzas, Cuba. {alexander.chavez, tony, hector.davila, yoan.gutierrez, armando.collazo, jose.abreu}@umcc.cu necessarily a student). In addition, STS differs Abstract from TE and Paraphrase in that, rather than being a binary yes/no decision, STS is a This paper describes the specifications and results of UMCC_DLSI system, which similarity-graded notion (e.g. a student is more participated in the Semantic Textual similar to a person than a dog to a person). Similarity task (STS) of SemEval-2013. Our This graded bidirectional is useful for NLP supervised system uses different types of tasks such as Machine Translation (MT), lexical and semantic features to train a Information Extraction (IE), Question Bagging classifier used to decide the correct Answering (QA), and Summarization. Several option. Related to the different features we semantic tasks could be added as modules in the can highlight the resource ISR-WN used to STS framework, “such as Word Sense extract semantic relations among words and Disambiguation and Induction, Lexical the use of different algorithms to establish Substitution, Semantic Role Labeling, Multiword semantic and lexical similarities. In order to establish which features are the most Expression detection and handling, Anaphora appropriate to improve STS results we and Co-reference resolution, Time and Date 1 participated with three runs using different resolution and Named Entity, among others” set of features.
    [Show full text]
  • Exploring the Integration of Wordnet and Framenet
    Exploring the Integration of WordNet and FrameNet Egoitz Laparra German Rigau Montse Cuadros IXA group, UPV/EHU IXA group, UPV/EHU TALP Research Center, UPC Donostia, Spain Donostia, Spain Barcelona, Spain [email protected] [email protected] [email protected] Abstract However, building large and rich enough predi- cate models for broad–coverage semantic process- This paper presents a novel automatic approach to ing takes a great deal of expensive manual effort partially integrate FrameNet and WordNet. In that involving large research groups during long peri- way we expect to extend FrameNet coverage, to ods of development. Thus, the coverage of cur- enrich WordNet with frame semantic information rently available predicate-argument resources is and possibly to extend FrameNet to languages other still unsatisfactory. For example, (Burchardt et than English. The method uses a knowledge-based al., 2005) or (Shen and Lapata, 2007) indicate the Word Sense Disambiguation algorithm for match- limited coverage of FrameNet as one of the main ing the FrameNet lexical units to WordNet synsets. problems of this resource. In fact, FrameNet1.3 Specifically, we exploit a graph-based Word Sense covers around 10,000 lexical-units while for in- Disambiguation algorithm that uses a large-scale stance, WordNet3.0 contains more than 150,000 knowledge-base derived from existing resources. words. Furthermore, the same effort should be in- We have developed and tested additional versions vested for each different language (Subirats and of this algorithm showing substantial improvements Petruck, 2003). Following the line of previous over state-of-the-art results. Finally, we show some works (Shi and Mihalcea, 2005), (Burchardt et al., examples and figures of the resulting semantic re- 2005), (Johansson and Nugues, 2007), (Pennac- source.
    [Show full text]